Implement Car Accident Detection System on Dashboard Camera by Faster R-CNN

Abstract

The invention of the vehicle shortens the distance between people but it brings considerable danger Car accidents will cause huge social costs and harm people's lives and property Therefore in recent years research on car accidents has gradually increased Taiwan is a densely populated country and most people use motorcycles as their means of transportation Thus Taiwan's car accident casualty rate is one of the highest in the world It is important to deal with problems related to car accidents in Taiwan Most of the relevant literature which analyzes the sensor information on the vehicle to determine whether there is a car accident cannot preserve the circumstances so it is impossible to judge the traffic accident responsibility We use the deep learning object detection method Faster Region-based Convolutional Neural Network(Faster R-CNN) to instantly identify car accidents And we implement it on the Android system We write apps through Android Studio which can judge car accidents while photographing

Date of Award	2019
Original language	English
Supervisor	Ren-Shiou Liu (Supervisor)